Help
Options
Didn't know it?
click below
click below
Knew it?
click below
click below
Don't Know
Remaining cards (0)
Know
retry
shuffle
restart
0:00
Embed Code - If you would like this activity on your web page, copy the script below and paste it into your web page.
Normal Size Small Size show me how
Normal Size Small Size show me how
AI
ARTIFICIAL INTELLIGENCE FOR BEGINNERS
| Key TERMS | EXPLAINATION |
|---|---|
| AI | AI refers to the development of computer systems that can perform tasks that typically require human intelligence. |
| REACTIVE MACHINES | Only respond to immediate situations and don't have long-term memory. |
| LIMITED MEMORY SYSTEMS | Use past experiences to inform current decisions, |
| THEORY OF MIND SYSTEMS | Attempt to understand the mental states of others. |
| SELF AWARE SYSTEMS | Have a sense of self and consciousness. |
| PROBLEM SOLVING ALGORITHMS | Problem-solving involves finding a solution to a particular challenge or question. |
| DEPTH-FIRST SEARCH | Another popular algorithm is the depth-first search, which involves exploring a graph or tree by traversing down one path as far as possible before backtracking and exploring other paths. |
| SEARCH ALGORITHMS | Methods for navigating through large amounts of data or information in search of a specific piece of data. |
| A* algorithm | Commonly used in path-finding tasks, such as finding the shortest route between two points. |
| KNOWLEDGE REPRESENTATION & REASONING | Essential components of artificial intelligence that allow machines to understand and interpret complex information. |
| EXPERT SYSTEMS | Computer programs designed to solve complex problems in a specific domain. |
| NATURAL LANGUAGE PROCESSING | Allows machines to understand and interpret human language. |
| MACHINE LEARNING | Rapidly growing field within artificial intelligence that involves creating algorithms and models that allow computers to learn from data, recognize patterns, and make decisions without being explicitly programmed. |
| SUPERVISED LEARNING | Uses labelled data to train models for making predictions. |
| UNSUPERVISED LEARNING ALGORITHM (ULA) | Identifies patterns and relationships in unlabeled data. |
| REINFORCEMENT LEARNING | Trains an agent to make decisions based on feedback. |
| REASONING | The process of using the information stored in knowledge representation to make logical deductions and conclusions. |
| LINEAR REGRESSION | This algorithm is used to predict continuous values, such as the price of a house or a stock. It works by finding the line of best fit through the data. |
| LOGISTIC REGRESSION | This algorithm is used to predict binary values, such as yes or no, or true or false. It works by finding the boundary between the positive and negative examples. |
| DECISION TREES | This algorithm is used to make decisions based on multiple inputs. It works by creating a tree of decisions, where each node represents a decision, and the leaves represent the final outcome. |
| K-MEANS CLUSTERING | ULA. This algorithm is used to group similar data points together. It works by dividing the data into k groups, where k is a user-defined number, and then moving the data points to the centre of the closest group. |
| PRINCIPAL COMPONENT ANALYSIS (PCA) | ULA. This algorithm is used to reduce the dimensionality of the data. It works by finding the directions of maximum variance in the data and then projecting the data onto these directions. |
| AUTOENCODER | ULA. This algorithm is used to learn a compact representation of the data. It works by training a neural network to encode the data into a lower-dimensional representation and then decode the representation back into the original data. |
| REINFORCEMENT LEARNING ALGORITHMS (RLA) | The Reinforcement Learning Algorithms have four different branches: Q-learning, SARSA, Policy gradient methods, and Actor-critic methods. |
| Q-LEARNING | This algorithm learns the optimal action-value function by iteratively updating the Q-value of a state-action pair based on the reward received and the estimated value of the next state. |
| SARSA | This algorithm is similar to Q-learning, but instead of learning the optimal action-value function, it learns the Q-value of the current policy. |
| POLICY GRADIENT METHODS | These algorithms directly optimize the policy function that maps states to actions, using gradient ascent to update the policy parameters based on the observed rewards. |
| ACTOR-CRITIC METHODS | These algorithms combine policy gradient methods with value-based methods, where the critic estimates the value of state-action pairs, and the actor updates the policy based on these estimates. |
| PREPROCESSING TEXT DATA | A critical step in Natural Language Processing (NLP). It involves preparing the text data for further analysis and modeling. Cleaning, normalizing, and transforming the text data into a format that can be fed into the machine learning algorithm. |
| TEXT DATA | Doesn't follow a specific format or scheme and can contain noise, irrelevant information, and inconsistencies. |
| TOKENIZATION | A preprocessing technique (pt) that consists of breaking down the text data into individual words or tokens. |
| STOP WORD REMOVER | A PT that consists of removing common words that don't carry much meaning, such as "a", "an", and "the". |
| STEMMING & LEMMATIZATION | Reducing words to their base form to group them together and reduce the dimensionality of the dataset. |
| PART-OF-SPEECH (POS) TAGGING | Assigning parts of speech to words in a sentence. |
| NAMED ENTITY RECOGNITION (NER) | Identifying and categorizing named entities in text, such as people, organizations, and locations. For example, in sentiment analysis, preprocessing text data.It looks for patterns and context clues to identify and extract specific entities. |
| TEXT CLASSIFICATION | Categorizing texts into predefined categories. One of the most popular approaches to text classification is the use of machine learning algorithms, specifically supervised learning. |
| EXAMPLE OF TEXT CLASSIFICATION | The work done by the New York Times in classifying their articles into topics. They developed an algorithm that categorizes their articles into one or more of the 24 topics. |
| SENTIMENT ANALYSIS | Determining the emotional tone or attitude in a piece of text. It's a type of natural language processing that has become increasingly popular in recent years, with many companies using it to analyze customer feedback, reviews, and social media posts. |
| APPROACH TO SENTIMENT ANALYSIS | Machine learning algorithms to classify text as positive, negative, or neutral. Algorithms are trained on large datasets of text labelled with their corresponding sentiment, allowing them to learn patterns in the data and make predictions on new text. |
| EXAMPLE OF SENTIMENT ANALYSIS | Airlines have used sentiment analysis to analyze customer feedback from social media and reviews to identify trends and areas for improvement. |
| STEP 1 OF SENTIMENT ANALYSIS | The text is preprocessed to remove any noise or irrelevant information. |
| STEP 2 OF SENTIMENT ANALYSIS | Features are extracted from the text, such as the frequency of certain words or phrases. |
| STEP 3 OF SENTIMENT ANALYSIS | A machine learning algorithm is trained on these features to classify the text as positive, negative, or neutral. |
| ENTITY | Things like people, places, organizations, dates, and more. |
| EXAMPLE OF NAME ENTITY RECOGNITION (NER) | Say we have a sentence like "Lyric Info was born in California in 1975." NER would recognize "Lyric Info" as a person's name, "California" as a location, and "1975" as a date. This information could then be used for further analysis or processing. |
| ROBOTICS | AI is used to create machines that can perform tasks that were once thought impossible for machines. |
| APPLICATIONS OF AI IN ROBOTICS | Creating humanoid robots that can mimic human movements and perform tasks that previously were only possible for humans. |
| IMAGE AND SPEECH RECOGNITION | Allow machines to process and understand visual and auditory information like humans do, enabling them to identify objects and people, understand speech, and even generate text and speech. |
| IMAGE RECOGNITION | The process of identifying and classifying objects or people within digital images or video. |
| EXAMPLE OF IR | In the medical field. Radiologists and doctors can use machine learning algorithms to analyze medical images, such as X-rays and MRIs, to quickly and accurately diagnose diseases. |
| SPEECH RECOGNITION | Involves converting spoken language into text. |
| EXAMPLE OF SR | By implementing speech recognition technology, call centers can automatically transcribe and analyze calls to improve customer service and identify areas for improvement. |
| NATURAL LANGUAGE GENERATION (NLG) | The ability of a computer to write sentences that look like they were written by a human being. |
| EXPERT SYSTEMS | AI-based computer system that emulates the decision-making ability of a human expert in a particular field. |
| HOW EXPERT SYSTEMS FUNCTION | They use a knowledge base, which contains information and rules about a specific domain, and an inference engine, which applies logical reasoning to the knowledge base to arrive at a conclusion or recommendation. |
| MYCIN | An expert system developed in the 1970s, which was designed to help diagnose bacterial infections and recommend appropriate antibiotics. |
| DENDRAL | An expert system developed in the 1960s, which was used to identify unknown organic compounds based on their mass spectra. |
Created by:
Lyric411
Popular Computers sets